Hallucination Detection on SC-Vicuna (AUCPR)
91.1AUCPRSELFCHECKGPT
Evaluation Results
| Method | Links | |
|---|---|---|
| SELFCHECKGPTDetector=LLaMA 3.1, Future context=true2025.07 | 91.1 | |
| SELFCHECKGPTDetector=Gemma 3, Future context=true2025.07 | 90.7 | |
| SCDetector=LLaMA 3.1, Future context=true2025.07 | 90.3 | |
| SELFCHECKGPTDetector=LLaMA 3.1, Future context=false2025.07 | 90.2 | |
| SELFCHECKGPTDetector=Gemma 3, Future context=false2025.07 | 89.3 | |
| DIRECTDetector=LLaMA 3.1, Future context=true2025.07 | 89.2 | |
| SCDetector=Gemma 3, Future context=true2025.07 | 88.5 | |
| SELFCHECKGPTDetector=Qwen 2.5, Future context=false2025.07 | 88.5 | |
| DIRECTDetector=LLaMA 3.1, Future context=false2025.07 | 88.4 | |
| SELFCHECKGPTDetector=Qwen 2.5, Future context=true2025.07 | 88.4 | |
| SCDetector=LLaMA 3.1, Future context=false2025.07 | 88.1 | |
| DIRECTDetector=Qwen 2.5, Future context=false2025.07 | 87.9 | |
| DIRECTDetector=Qwen 2.5, Future context=true2025.07 | 87.7 | |
| SCDetector=Gemma 3, Future context=false2025.07 | 87.5 | |
| SCDetector=Qwen 2.5, Future context=true2025.07 | 86 | |
| DIRECTDetector=Gemma 3, Future context=true2025.07 | 84.9 | |
| DIRECTDetector=Gemma 3, Future context=false2025.07 | 84.6 | |
| SCDetector=Qwen 2.5, Future context=false2025.07 | 84.4 |